Download PDF
Methods Inf Med 2020; 59(01): 018-030
DOI: 10.1055/s-0040-1710382
Original Article

An Augmented Model with Inferred Blood Features for the Self-diagnosis of Metabolic Syndrome

Tianshu Zhou
1   Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, People's Republic of China
2   Connected Healthcare Big Data Research Center, Zhejiang Lab, Hangzhou, People's Republic of China
,
Ying Zhang
1   Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, People's Republic of China
2   Connected Healthcare Big Data Research Center, Zhejiang Lab, Hangzhou, People's Republic of China
,
Chengkai Wu
1   Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, People's Republic of China
,
Chao Shen
3   Health Management Center, The First Affiliated Hospital, Medical School of Zhejiang University, Hangzhou, People's Republic of China
,
Jingsong Li
1   Engineering Research Center of EMR and Intelligent Expert System, Ministry of Education, Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou, People's Republic of China
2   Connected Healthcare Big Data Research Center, Zhejiang Lab, Hangzhou, People's Republic of China
,
Zhong Liu
3   Health Management Center, The First Affiliated Hospital, Medical School of Zhejiang University, Hangzhou, People's Republic of China
› Author Affiliations Funding This work was supported by the National Natural Science Foundation of China (No. 81771936), the National Key Research and Development Program of China (No. 2018YFC0116901), the Fundamental Research Funds for the Central Universities (No. 2020FZZX002-08) and the Major Scientific Project of Zhejiang Lab (No. 2018DG0ZX01).
› Further Information
   Permissions and Reprints

Abstract

Background and Objectives The penetration rate of physical examinations in China is substantially lower than that in developed countries. Therefore, an auxiliary approach that does not depend on hospital health checks for the diagnosis of metabolic syndrome (MetS) is needed.

Methods In this study, we proposed an augmented method with inferred blood features that uses self-care inputs available at home for the auxiliary diagnosis of MetS. The dataset used for modeling contained data on 91,420 individuals who had at least 2 consecutive years of health checks. We trained three separate models using a regularized gradient-boosted decision tree. The first model used only home-based features; additional blood test data (including triglyceride [TG] data, fasting blood glucose data, and high-density lipoprotein cholesterol [HDL-C] data) were included in the second model. However, in the augmented approach, the blood test data were manipulated using multivariate imputation by chained equations prior to inclusion in the third model. The performance of the three models for MetS auxiliary diagnosis was then quantitatively compared.

Results The results showed that the third model exhibited the highest classification accuracy for MetS in comparison with the other two models (area under the curve [AUC]: 3rd vs. 2nd vs. 1st = 0.971 vs. 0.950 vs. 0.905, p < 0.001). We further revealed that with full sets of the three measurements from earlier blood test data, the classification accuracy of MetS can be further improved (AUC: without vs. with = 0.971 vs. 0.993). However, the magnitude of improvement was not statistically significant at the 1% level of significance (p = 0.014).

Conclusion Our findings demonstrate the feasibility of the third model for MetS homecare applications and lend novel insights into innovative research on the health management of MetS. Further validation and implementation of our proposed model might improve quality of life and ultimately benefit the general population.

Keywords

self-care - machine learning - systolic blood pressure - diastolic blood pressure - metabolic syndrome

Note

Human and/or animal subjects were not included in the project.




Publication History

Received: 04 December 2018

Accepted: 15 March 2020

Article published online:
24 August 2020

© 2020. Thieme. All rights reserved.

Georg Thieme Verlag KG
Stuttgart · New York

 

  • References

  • 1 Alberti KGMM, Zimmet P, Shaw J. Metabolic syndrome—a new world-wide definition. A consensus statement from the International Diabetes Federation. Diabet Med 2006; 23 (05) 469-480
    CrossrefPubMedGoogle Scholar
  • 2 Zhang L, Cui HY, Liu AP. Association of hypertension, diabetes, dyslipidemia, and metabolic syndrome with overweight/obesity. Zhongguo Manxingbing Yufang Yu Kongzhi 2009; 17 (06) 561-563 . Doi: 10.16386/j.cjpccd.issn.1004-6194.2009.06.019
    PubMedGoogle Scholar
  • 3 Normann J, Mueller M, Biener M, Vafaie M, Katus HA, Giannitsis E. Effect of older age on diagnostic and prognostic performance of high-sensitivity troponin T in patients presenting to an emergency department. Am Heart J 2012; 164 (05) 698-705.e4
    CrossrefPubMedGoogle Scholar
  • 4 Zang YM, Rong FAN. Annihilation of the first health-killer (cardiovascular diseases) in cooperation with multi-branches of science. Chin Heart J 2006; (05) 483-488
    PubMedGoogle Scholar
  • 5 Aleksandrova K, Boeing H, Jenab M. , et al. Metabolic syndrome and risks of colon and rectal cancer: the European prospective investigation into cancer and nutrition study. Cancer Prev Res (Phila) 2011; 4 (11) 1873-1883
    CrossrefPubMedGoogle Scholar
  • 6 Baranova A, Tran TP, Birerdinc A, Younossi ZM. Systematic review: association of polycystic ovary syndrome with metabolic syndrome and non-alcoholic fatty liver disease. Aliment Pharmacol Ther 2011; 33 (07) 801-814
    CrossrefPubMedGoogle Scholar
  • 7 Chen J, Kong X, Jia X. , et al. Association between metabolic syndrome and chronic kidney disease in a Chinese urban population. Clin Chim Acta 2017; 470: 103-108
    CrossrefPubMedGoogle Scholar
  • 8 Wei C, Yu Z. Analysis of correlation factors of hyperuricemia with metabolic syndrome and its related diseases in elderly male. Fudan Univ J Med Sci 2007; (03) 434-437 . Doi: 10.3969/j.issn.1672-8467.2007.03.026
    PubMedGoogle Scholar
  • 9 Lindkvist B, Almquist M, Bjørge T. , et al. Prospective cohort study of metabolic risk factors and gastric adenocarcinoma risk in the metabolic syndrome and cancer project (Me-Can). Cancer Causes Control 2013; 24 (01) 107-116
    CrossrefPubMedGoogle Scholar
  • 10 Raviv NV, Sakhuja S, Schlachter M, Akinyemiju T. Metabolic syndrome and in-hospital outcomes among pancreatic cancer patients. Diabetes Metab Syndr 2017; 11 (Suppl. 02) S643-S650
    CrossrefPubMedGoogle Scholar
  • 11 Ogbera AO. Prevalence and gender distribution of the metabolic syndrome. Diabetol Metab Syndr 2010; 2 (01) 1-5
    CrossrefPubMedGoogle Scholar
  • 12 Xi B, He D, Hu Y, Zhou D. Prevalence of metabolic syndrome and its influencing factors among the Chinese adults: the China Health and Nutrition Survey in 2009. Prev Med 2013; 57 (06) 867-871
    CrossrefPubMedGoogle Scholar
  • 13 Hsieh SD, Muto T. A simple and practical index for assessing the risk of metabolic syndrome during routine health checkups [in Japanese]. Nihon Rinsho 2004; 62 (06) 1143-1149
    PubMedGoogle Scholar
  • 14 China NBoSo. China Statistical Yearbook 2017. China Statistic Press; Beijing, China: 2017
    Google Scholar
  • 15 Jiao Y, Hu R. Analysis of Current Situation of Residents Treated and Influence Factors in China. China Health Insurance; Beijing, China: 2012
    Google Scholar
  • 16 Ichikawa D, Saito T, Oyama H. Impact of predicting health-guidance candidates using massive health check-up data: a data-driven analysis. Int J Med Inform 2017; 106: 32-36
    CrossrefPubMedGoogle Scholar
  • 17 Shimoda A, Ichikawa D, Oyama H. Prediction models to identify individuals at risk of metabolic syndrome who are unlikely to participate in a health intervention program. Int J Med Inform 2018; 111: 90-99
    CrossrefPubMedGoogle Scholar
  • 18 Shimoda A, Ichikawa D, Oyama H. Using machine-learning approaches to predict non-participation in a nationwide general health check-up scheme. Comput Methods Programs Biomed 2018; 163: 39-46
    CrossrefPubMedGoogle Scholar
  • 19 Ryu SH, Park H, Mieun Y. Correlation between serum uric acid, BMI, fasting blood sugar, TG and HDL in Korean health check examinees. Cancer Res 2010; 70 (02) 655-665
    CrossrefPubMedGoogle Scholar
  • 20 Alberti KGMM, Eckel RH, Grundy SM. , et al; International Diabetes Federation Task Force on Epidemiology and Prevention, Hational Heart, Lung, and Blood Institute, American Heart Association; World Heart Federation, International Atherosclerosis Society, International Association for the Study of Obesity. Harmonizing the metabolic syndrome: a joint interim statement of the International Diabetes Federation Task Force on Epidemiology and Prevention; National Heart, Lung, and Blood Institute; American Heart Association; World Heart Federation; International Atherosclerosis Society; and International Association for the Study of Obesity. Circulation 2009; 120 (16) 1640-1645
    CrossrefPubMedGoogle Scholar
  • 21 Gurka MJ, Filipp SL, Musani SK, Sims M, DeBoer MD. Use of BMI as the marker of adiposity in a metabolic syndrome severity score: derivation and validation in predicting long-term disease outcomes. Metabolism 2018; 83: 68-74
    CrossrefPubMedGoogle Scholar
  • 22 Mohamad IB, Usman D. Standardization and its effects on K-means clustering algorithm. Res J Appl Sci Eng Technol 2013; 6 (17) 3299-3303
    CrossrefPubMedGoogle Scholar
  • 23 Chawla NV, Lazarevic A, Hall LO, Bowyer KW. SMOTEBoost: improving prediction of the minority class in boosting. Paper presented at: Knowledge Discovery in Databases: Pkdd 2003, European Conference on Principles and Practice of Knowledge Discovery in Databases; September 22–26, 2003; Cavtat-Dubrovnik, Croatia:
    PubMedGoogle Scholar
  • 24 El-Sayed AA, Mahmood MAM, Meguid NA, Hefny HA. Handling autism imbalanced data using synthetic minority over-sampling technique (SMOTE). Paper presented at: Complex Systems; 2016; Marrakech, Morocco
    PubMedGoogle Scholar
  • 25 Torgo L. 2010 Data Mining with R, learning with case studies Chapman and Hall/CRC. URL: http://www.dcc.fc.up.pt/~ltorgo/DataMiningWithR
    PubMed
  • 26 Buuren SV, Groothuisoudshoorn K. mice: multivariate imputation by chained equations in R. J Stat Softw 2017; 45 (03) 1-67
    PubMedGoogle Scholar
  • 27 Chen T, Guestrin C. XGBoost: a scalable tree boosting system. Paper presented at: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016; San Francisco, California, USA
    PubMedGoogle Scholar
  • 28 Azur MJ, Stuart EA, Frangakis C, Leaf PJ. Multiple imputation by chained equations: what is it and how does it work?. Int J Methods Psychiatr Res 2011; 20 (01) 40-49
    CrossrefPubMedGoogle Scholar
  • 29 Chen T, Tong H, Benesty M, Khotilovich V, Yuan T. xgboost: extreme gradient boosting. Paper presented at: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM; San Francisco, California, USA 2016;785–794
    PubMedGoogle Scholar
  • 30 Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006; 27 (08) 861-874
    CrossrefPubMedGoogle Scholar
  • 31 Flach PA, Kull M. Precision-RECALL-GAIN CURVES: PR analysis done right. Paper presented at: International Conference on Neural Information Processing Systems; Montreal, CANADA 2015
    PubMedGoogle Scholar
  • 32 Melo F. Area under the ROC Curve. New York, NY: Springer; 2013
    CrossrefGoogle Scholar
  • 33 Taghizadeh S, Alizadeh M. The role of lipids in the pathogenesis of metabolic syndrome in adolescents. Exp Clin Endocrinol Diabetes 2018; 126 (01) 14-22
    Article in Thieme ConnectPubMedGoogle Scholar
  • 34 Amiot MJ, Riva C, Vinet A. Effects of dietary polyphenols on metabolic syndrome features in humans: a systematic review. Obes Rev 2016; 17 (07) 573-586
    CrossrefPubMedGoogle Scholar
  • 35 Srikanthan K, Feyh A, Visweshwar H, Shapiro JI, Sodhi K. Systematic review of metabolic syndrome biomarkers: a panel for early detection, management, and risk stratification in the West Virginian population. Int J Med Sci 2016; 13 (01) 25-38
    CrossrefPubMedGoogle Scholar
  • 36 O'Neill S, Bohl M, Gregersen S, Hermansen K, O'Driscoll L. Blood-based biomarkers for metabolic syndrome. Trends Endocrinol Metab 2016; 27 (06) 363-374
    CrossrefPubMedGoogle Scholar
  • 37 Onat A, Can G, Çoban N. , et al. Lipoprotein(a) level and MIF gene variant predict incident metabolic syndrome and mortality. J Investig Med 2016; 64 (02) 392-399
    CrossrefPubMedGoogle Scholar
  • 38 Ridker PM, Buring JE, Cook NR, Rifai N. C-reactive protein, the metabolic syndrome, and risk of incident cardiovascular events: an 8-year follow-up of 14,719 initially healthy American women. Circulation 2003; 107 (03) 391-397
    CrossrefPubMedGoogle Scholar
  • 39 Magnussen CG, Cheriyan S, Sabin MA. , et al. Continuous and dichotomous metabolic syndrome definitions in youth predict adult type 2 diabetes and carotid artery intima media thickness: the cardiovascular risk in Young Finns Study. J Pediatr 2016; 171: 97-103.e1 –3
    CrossrefPubMedGoogle Scholar
  • 40 Prokopowicz Z, Malecka-Tendera E, Matusik P. Predictive value of adiposity level, metabolic syndrome, and insulin resistance for the risk of nonalcoholic fatty liver disease diagnosis in obese children. Can J Gastroenterol Hepatol 2018; 2018 (01) 9465784
    PubMedGoogle Scholar
  • 41 Boudreau DM, Malone DC, Raebel MA. , et al. Health care utilization and costs by metabolic syndrome risk factors. Metab Syndr Relat Disord 2009; 7 (04) 305-314
    CrossrefPubMedGoogle Scholar
  • 42 Kan YC, Chen KH, Lin HC. Developing a Ubiquitous Health Management System with Healthy Diet Control for Metabolic Syndrome Healthcare in Taiwan. Comput Meth Prog Bio 2017; 144: 37-48
    CrossrefPubMedGoogle Scholar
  • 43 Hwang LC, Bai CH, You SL, Sun CA, Chen CJ. Description and prediction of the development of metabolic syndrome: a longitudinal analysis using a Markov model approach. PLoS One 2013; 8 (06) e67436
    CrossrefPubMedGoogle Scholar
  • 44 Hirose H, Takayama T, Hozawa S, Hibi T, Saito I. Prediction of metabolic syndrome using artificial neural network system based on clinical data including insulin resistance index and serum adiponectin. Comput Biol Med 2011; 41 (11) 1051-1056
    CrossrefPubMedGoogle Scholar
  • 45 Medynskiy Y, Mynatt ED. Salud!: an open infrastructure for developing and deploying health self-management applications. Paper presented at: Pervasive Computing Technologies for Healthcare; Dublin, Ireland 2011
    PubMedGoogle Scholar
  • 46 Bivins R, Marland H. Weighting for health: management, measurement and self-surveillance in the modern household. Soc Hist Med 2016; 29 (04) 757-780
    CrossrefPubMedGoogle Scholar
  • 47 Borda A, Gilbert C, Gray K, Prabhu D. Consumer wearable information and health self management by older adults. Stud Health Technol Inform 2018; 246: 42-61
    PubMedGoogle Scholar